© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 51941
    Prev
    Next
    INDEX
    Explanations

    security vulnerabilities and technical implementation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Asw
    0.42
    橥
    0.42
    시오
    0.41
    ifed
    0.41
    로는
    0.40
     if
    0.40
    리로
    0.39
    ificado
    0.39
    게요
    0.39
    اسة
    0.39
    POSITIVE LOGITS
    -
    0.51
    पाठी
    0.50
     dones
    0.48
    UB
    0.46
    Rash
    0.44
    ूपी
    0.43
     Stretch
    0.43
     доход
    0.43
     другу
    0.42
     спорт
    0.42
    Activations Density 0.003%

    No Known Activations